GitHub - intel/ipex-llm: Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max

テクノロジーカテゴリーの変更を依頼記事元:

github.com/intel

9users がブックマークコメント

記事へのコメント1件

注目コメント
新着コメント

misshiki “IPEX-LLMは、 Intel CPU および GPU でLLM を非常に低いレイテンシで実行するための PyTorch ライブラリです。”

2024/04/08 リンク

注目コメント算出アルゴリズムの一部にLINEヤフー株式会社の「建設的コメント順位付けモデルAPI」を使用しています

リンクを埋め込む

以下のコードをコピーしてサイトに埋め込むことができます

<iframe marginwidth="0" marginheight="0" src="https://b.hatena.ne.jp/entry.parts?url=https%3A%2F%2F2.zoppoz.workers.dev%3A443%2Fhttps%2Fgithub.com%2Fintel%2Fipex-llm" scrolling="no" frameborder="0" height="230" width="500"><div class="hatena-bookmark-detail-info"><a href="https://github.com/intel/ipex-llm">GitHub - intel/ipex-llm: Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max</a><a href="https://b.hatena.ne.jp/entry/s/github.com/intel/ipex-llm">はてなブックマーク - GitHub - intel/ipex-llm: Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max</a></div></iframe>

プレビュー

規約違反を報告

いまの話題をアプリでチェック！

バナー広告なし
ミュート機能あり
ダークモード搭載

アプリをダウンロード

GitHub - intel/ipex-llm: Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max

[2025/04] We added support of PyTorch 2.6 for Intel GPU. [2025/03] We added support for Gemma3 mo... [2025/04] We added support of PyTorch 2.6 for Intel GPU. [2025/03] We added support for Gemma3 model in the latest llama.cpp Porta ble Zip. [2025/03] We can now run DeepSeek-R1-671B-Q4_K_M with 1 or 2 Arc A770 on Xeon using the latest llama.cpp Porta ble Zip. [2025/02] We added support of llama.cpp Porta ble Zip for Intel GPU (both Windows and Linux) and NPU (Windows only). [2025/02] We added support